Systems and efficient execution · MLD-0342
Dynamic batching
Grouping incoming inference requests at runtime, often using a short wait window.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Combine independent classification requests on a GPU.
Original caveat
Dynamic batching is broader than token-level continuous batching.
Context and aliases
Level: Advanced. Stages: Training · Inference · Deployment.
Tags: DL · LLM · SLM · Systems.
Aliases: None recorded.
Related concepts
Concepts linking here
Original references
- PyTorch Fully Sharded Data Parallel ↗ · Consulted
- PyTorch documentation ↗ · Reference link
- vLLM documentation ↗ · Consulted
- Original reference URL ↗